Taimoor Khawaja

From ICSL

	Office: Room 227, Intelligent Systems Control laboratory (ICSL) Manufacturing Research Center (MaRC) Georgia Institute of Technology 813 Ferst Drive, N.W. Atlanta, Georgia 30332-0560 U.S.A. Telephone: +1(404) 894-4130 Fax: +1(404) 894-3971 email: Taimoor

About

I am a PhD student in the School of Electrical and Computer Engineering at GeorgiaTech. I am working on hybrid architectures for Integraed Diagnosis and Prognosis of Manufacturing Systems. My research is motivated by Support Vector Machines as applied to classification and regression problems.

I joined Georgia Tech in 2001 at the school of Electrical and Computer Engineering, and earned my Master of Science Degree in May 2002. I received my Bachelor of Engineering degree from the National University of Sciences and Technology, Rawalpindi, Pakistan in November 1998.

Research

My Research focuses on realizing algorithms that can efficiently and accurately perform real-time system diagnosis and prognosis. Manufacturing systems are a major application area for us. My design philosophy is largely centered designing data-driven architectures using basic modeling information of the underlying process-thus the "hybrid" approach. The core algorithms of my work are based on a statistical learning tool called Support Vector Machines and its primary variant, Support Vector Regression. Other components that tie in with the core are schemes based on Blind Deconvolution, Genetic Algorithms, Reinforcement Learning and Bayesian Inference Modeling.

Publications

Conference Articles
B. Wu, A. Saxena, T. S. Khawaja, R. Patrick, G. Vachtsevanos, P. Sparis, " Data Analysis and Feature Selection for Fault Diagnosis of Helicopter Planetary Gears," IEEE Autotestcon 2004	PDF
Taimoor Khawaja, George Vachtsevanos and Becky Wu, "[Reasoning about Uncertainty in Prognosis: A Confidence Prediction Neural Network Approach]]," NAFIPS 2005
Bin Zhang, Taimoor Khawaja, Romano Patrick, George Vachtsevanos , Blind Deconvolution De-noising for Helicopter Vibration Data, American Control Conference, 2007. ACC '07	PDF